How to Use the NPM Registry MCP in Google ADK

Q: How do I get general stats about the registry?

Use the getregistrymeta tool to check the total package count and backend metadata. This is useful for verifying that your connection to the registry is active.

Feed real-time package data into your long-context Gemini models using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NPM Registry MCP to Google ADK

Create your Vinkius account to connect NPM Registry to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup NPM Registry with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze dependency trees in long-context windows

The `get_package` tool fetches detailed package metadata, feeding massive dependency trees directly into Gemini's million-token context window. This allows your enterprise agents to evaluate complex codebases without running out of memory. Combining this data with your BigQuery tables helps you spot outdated components across your entire infrastructure. You get a single, clear source of truth for your internal development teams.

Audit version signatures with Google ADK

Your LLM agent relies on `get_package_version` to fetch exact version specs, tarball locations, and package integrity hashes. This tool provides the raw data needed to verify that your deployments match public registry records. Instead of relying on manual terminal checks, your automated pipelines verify package authenticity on the fly. The agent flags mismatched signatures before any code gets pulled into your cloud build.

Filter the ecosystem using advanced search

The `search_packages` tool lets your agent query the NPM registry using precise qualifiers like author, keywords, or stability flags. This MCP integration means your agent can automatically discover and filter packages based on enterprise criteria. If a package is flagged as unstable, your agent can search for alternatives from the same author or with similar keywords. This keeps your dependencies safe and maintained.

Setup guide

Set up NPM Registry MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with NPM Registry tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="NPM Registry_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NPM Registry tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by NPM Registry. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect NPM Registry now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about NPM Registry MCP in Google ADK

You initialize the toolset using the streamable HTTP server parameters in Python. Pass that toolset directly to your LlmAgent instance to expose the registry tools.

Yes, the toolset class allows you to pass an optional list of allowed tool names. This restricts the agent to specific actions like searching or checking versions.

It supports both transport mechanisms natively. For cloud deployments, the HTTP transport connects your agent to the managed MCP endpoint with a single token.

Use the `get_registry_meta` tool to check the total package count and backend metadata. This is useful for verifying that your connection to the registry is active.

All package names and search terms sent through the server are processed in memory within an isolated V8 sandbox. No query history or package details are written to persistent storage, keeping your proprietary dependency audits confidential.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript